Skip to content

Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.

Add Docker entrypoint for MCP server listing (#3075)

zhifu gao40539a5bfe33
diff --git a/docs/community_growth_20k.md b/docs/community_growth_20k.md
index 2406cd920..376ecf26a 100644
--- a/docs/community_growth_20k.md
+++ b/docs/community_growth_20k.md
@@ -131,6 +131,7 @@ Set `GITHUB_TOKEN` when running this from CI or a shared network so GitHub's pub
| `huggingface/optimum-intel#1801` OpenVINO support | Helps CPU and edge users evaluate Fun-ASR on Intel hardware | Watch for CI or reviewer feedback, then validate a minimal inference path before promoting it in FunASR docs. |
| `huggingface/speech-to-speech#319` SenseVoice STT handler | Adds SenseVoice/FunASR to local open-source voice-agent pipelines where low-latency STT is a core comparison point | Keep lint/import fixes on the PR head, explain optional `speech-to-speech[sensevoice]` install behavior, and answer handler-scope review quickly. |
| `livekit/agents#6176` FunASR/SenseVoice realtime STT plugin | Opens a path into LiveKit's realtime voice-agent ecosystem where local STT is evaluated alongside hosted providers | CI and CLA are green; avoid duplicate pings and monitor for maintainer review on plugin scope, package metadata, or optional dependency expectations. |
+| `punkpeye/awesome-mcp-servers#7153` FunASR MCP server listing | Exposes FunASR to a high-star MCP discovery list used by agent-tool builders looking for local speech tools | Keep the Dockerized stdio server entrypoint ready for Glama checks, then update the external PR only when there is a valid Glama score/badge or maintainer feedback. |
| `run-llama/llama_index#21958` FunASR endpoint reader | Puts FunASR behind a LlamaIndex reader for OpenAI-compatible transcription endpoints used in RAG and agent pipelines | Keep the endpoint contract clear, avoid forcing local `funasr` dependencies into the main package, and validate one request/response example when the author updates. |
| `run-llama/llama_index#21996` local FunASR reader | Gives LlamaIndex users a local SenseVoice/FunASR reader for private transcription workflows | Keep optional dependencies isolated, verify the reader does not affect default installs, and watch for maintainer guidance on package extras. |
| `mem0ai/mem0#5571` optional FunASR transcription helper | Adds local FunASR transcription to a high-star memory layer used by agent builders | Keep FunASR optional, make examples clear about local model downloads, and separate unrelated preview/deployment failures from code review. |
diff --git a/examples/mcp_server/Dockerfile b/examples/mcp_server/Dockerfile
new file mode 100644
index 000000000..5ab821ce8
--- /dev/null
+++ b/examples/mcp_server/Dockerfile
@@ -0,0 +1,21 @@
+FROM python:3.10-slim
+
+ENV PYTHONDONTWRITEBYTECODE=1 \
+ PYTHONUNBUFFERED=1 \
+ PIP_NO_CACHE_DIR=1 \
+ FUNASR_DEVICE=cpu
+
+WORKDIR /app
+
+RUN apt-get update \
+ && apt-get install -y --no-install-recommends \
+ ffmpeg \
+ libsndfile1 \
+ && rm -rf /var/lib/apt/lists/*
+
+RUN python -m pip install --upgrade pip \
+ && pip install funasr
+
+COPY funasr_mcp.py /app/funasr_mcp.py
+
+CMD ["python", "/app/funasr_mcp.py"]
diff --git a/examples/mcp_server/README.md b/examples/mcp_server/README.md
index 34e96c183..166208ad0 100644
--- a/examples/mcp_server/README.md
+++ b/examples/mcp_server/README.md
@@ -10,7 +10,23 @@
pip install funasr
```
-### 2. Configure your AI tool
+### 2. Optional: run with Docker
+
+The Dockerfile starts the MCP server over stdio and is suitable for MCP directory
+checks that initialize the server and call `tools/list`.
+
+```bash
+docker build -t funasr-mcp examples/mcp_server
+docker run --rm -i \
+ -e FUNASR_DEVICE=cpu \
+ -v /path/to/audio:/audio:ro \
+ funasr-mcp
+```
+
+When submitting this server to MCP directories such as Glama, use this folder as
+the Docker build context so the container entrypoint runs `funasr_mcp.py`.
+
+### 3. Configure your AI tool
**Claude Code** (`~/.claude.json`):
```json
diff --git a/scripts/collect_growth_metrics.py b/scripts/collect_growth_metrics.py
index 8e68fb868..3dd27e95d 100755
--- a/scripts/collect_growth_metrics.py
+++ b/scripts/collect_growth_metrics.py
@@ -35,6 +35,7 @@ DEFAULT_INTEGRATION_PRS = [
"huggingface/optimum-intel#1801",
"huggingface/speech-to-speech#319",
"livekit/agents#6176",
+ "punkpeye/awesome-mcp-servers#7153",
"run-llama/llama_index#21958",
"run-llama/llama_index#21996",
"mem0ai/mem0#5571",
diff --git a/tests/test_collect_growth_metrics.py b/tests/test_collect_growth_metrics.py
index 75e9724b8..ee814f6cd 100644
--- a/tests/test_collect_growth_metrics.py
+++ b/tests/test_collect_growth_metrics.py
@@ -90,6 +90,12 @@ def test_default_integration_prs_include_voice_agent_and_ml_discovery_lanes():
assert expected_prs.issubset(set(module.DEFAULT_INTEGRATION_PRS))
+def test_default_integration_prs_include_mcp_discovery_lanes():
+ module = load_growth_metrics_module()
+
+ assert "punkpeye/awesome-mcp-servers#7153" in module.DEFAULT_INTEGRATION_PRS
+
+
def test_default_integration_prs_exclude_archived_integration_prs():
module = load_growth_metrics_module()
diff --git a/tests/test_mcp_server_example.py b/tests/test_mcp_server_example.py
new file mode 100644
index 000000000..24058166f
--- /dev/null
+++ b/tests/test_mcp_server_example.py
@@ -0,0 +1,14 @@
+from pathlib import Path
+
+
+def test_mcp_server_example_has_glama_ready_dockerfile():
+ example_dir = Path(__file__).resolve().parents[1] / "examples" / "mcp_server"
+ dockerfile = example_dir / "Dockerfile"
+
+ assert dockerfile.is_file()
+
+ dockerfile_text = dockerfile.read_text()
+ assert "pip install" in dockerfile_text
+ assert "funasr" in dockerfile_text
+ assert "COPY funasr_mcp.py /app/funasr_mcp.py" in dockerfile_text
+ assert 'CMD ["python", "/app/funasr_mcp.py"]' in dockerfile_text